How to get the GPU info?

Question

I'm looking for a command that would give me the same info as:

cat /proc/cpuinfo 

Except for the GPU (type of the chip and memory, frequency).

Answer 1

I do not know of a direct equivalent, but lshw should give you the info you want, try:

sudo lshw -C display

(it also works without sudo but the info may be less complete/accurate)

You can also install the package lshw-gtk to get a GUI.

Answer 2

That type of information is non-standard, and the tools you will use to gather it vary widely.

The command glxinfo will give you all available OpenGL information for the graphics processor, including its vendor name, if the drivers are correctly installed.

To get clock speed information, there is no standard tool.

• For ATI/AMD GPUs running the old Catalyst driver, aticonfig --odgc should fetch the clock rates, and aticonfig --odgt should fetch the temperature data. I'm not familiar with AMDGPU-Pro, but a similar tool should exist.
• For NVIDIA GPUs, the nvidia-smi tool will show all of the information you could want, including clock speeds and usage statistics.

I am not aware of an equivalent tool for the open source drivers or for Intel or other GPUs, but other information on the hardware can be fetched from the lspci and lshw tools.

Answer 3

A blog post focusing on work done on the command-line is here:

http://www.cyberciti.biz/faq/howto-find-linux-vga-video-card-ram/

Find out the device ID:

 lspci | grep ' VGA ' | cut -d" " -f 1
03:00.0

You can then use this output with lspci again, forming two nested commands

lspci  -v -s  $(lspci | grep ' VGA ' | cut -d" " -f 1)

If you have more than 1 GPU card, try this equivalent command instead:

lspci | grep ' VGA ' | cut -d" " -f 1 | xargs -i lspci -v -s {}

Output from my system:

03:00.0 VGA compatible controller: NVIDIA Corporation G98 [Quadro NVS 295] (rev a1) (prog-if 00 [VGA controller])
    Subsystem: NVIDIA Corporation Device 062e
    Flags: bus master, fast devsel, latency 0, IRQ 24
    Memory at f6000000 (32-bit, non-prefetchable) [size=16M]
    Memory at ec000000 (64-bit, prefetchable) [size=64M]
    Memory at f4000000 (64-bit, non-prefetchable) [size=32M]
    I/O ports at dc80 [size=128]
    [virtual] Expansion ROM at f7e00000 [disabled] [size=128K]
    Capabilities: <access denied>
    Kernel driver in use: nvidia

EDIT: You can avoid the <access denied> by launching with sudo

So, (prefetchable) [size=64M) indicates that I have a 64-MB NVIDIA card. However, I don't, it's rather 256 MB. Why? See below.

To see how to get the most info and performance out of it, read an extremely comprehensive article on the Arch-Linux Wiki

https://wiki.archlinux.org/index.php/NVIDIA

For nvidia users, start with

nvidia-smi

(This works with the Nvidia drivers installed,but not with systems running the open-source 'nouveau' driver).

Output

Thu Dec 19 10:54:18 2013       
+------------------------------------------------------+                       
| NVIDIA-SMI 5.319.60   Driver Version: 319.60         |                       
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  Quadro NVS 295      Off  | 0000:03:00.0     N/A |                  N/A |
| N/A   73C  N/A     N/A /  N/A |      252MB /   255MB |     N/A      Default |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Compute processes:                                               GPU Memory |
|  GPU       PID  Process name                                     Usage      |
|=============================================================================|
|    0            Not Supported                                               |
+-----------------------------------------------------------------------------+

This indicates that I have a 256 MB GDDR3 Graphics card.

At this time, I don't know how to get this for Intel and AMD/ATI GPUs.

Answer 4

Run google-chrome and navigate to the URL about:gpu. If chrome has figured out how to use OpenGL, you will get extremely detailing information about your GPU.

Answer 5

Because you specified a command like cat for CPU's this is therefore the equivalent for GPU's. Specifically for Nvidia cards. It requires no software except the Nvidia device driver to be loaded.

The path here works for the cards I have. But yours may differ as others have pointed out in the comments.

1st GPU

> cat /proc/driver/nvidia/gpus/0/information
Model:       GeForce GTX 680
IRQ:         24
GPU UUID:    GPU-71541068-cded-8a1b-1d7e-a093a09e9842
Video BIOS:      80.04.09.00.01
Bus Type:    PCIe
DMA Size:    40 bits
DMA Mask:    0xffffffffff
Bus Location:    0000:01.00.0

2nd GPU

> cat /proc/driver/nvidia/gpus/1/information
Model:       GeForce GTX 580
IRQ:         33
GPU UUID:    GPU-64b1235c-51fc-d6f1-0f0e-fa70320f7a47
Video BIOS:      70.10.20.00.01
Bus Type:    PCIe
DMA Size:    40 bits
DMA Mask:    0xffffffffff
Bus Location:    0000:08.00.0

Answer 6

For Nvidia cards, type

nvidia-smi -q

Answer 7

clinfo

sudo apt-get install clinfo
clinfo

is the analogue of glxinfo but for OpenCL, my GPU setup is described at: https://stackoverflow.com/questions/7542808/how-to-compile-opencl-on-ubuntu/33483311#33483311 The output contains my GPU model among other things:

Number of devices                                 1
  Device Name                                     Quadro M1200

Ubuntu 20.04 Settings -> About

You can either open settings by clicking on top right menu, or you can just do:

• Super key (AKA Windows key)
• Type "about" and select the entry

So under "Graphics" I can see that my GPU model is

Quadro M1200/PCIe/SSE2

Some other things it can show:

• "Software Rendering" (Ubuntu 23.10): graphics card not working at all
• "NV117": I think this means it is using Nouveau

nvidia-settings

Mixes runtime with some static info.

More details: How do I check if Ubuntu is using my NVIDIA graphics card?

Answer 8

I do believe the best option for this is neofetch.

# Get neofetch
sudo add-apt-repository ppa:dawidd0811/neofetch
sudo apt update
sudo apt install neofetch
# Run neofetch
neofetch

This gives an output like this:

Answer 9

This is really not that complex For model and memory, here's a 1 liner that works for every video card I've tested it on regardless of manufacturer (Intel, AMD, NVIDIA):

GPU=$(lspci | grep VGA | cut -d ":" -f3);RAM=$(cardid=$(lspci | grep VGA |cut -d " " -f1);lspci -v -s $cardid | grep " prefetchable"| cut -d "=" -f2);echo $GPU $RAM

GPU= All this bit does is grab the 3rd field from 'lspci' output filtered via 'grep' for VGA which corresponds to the video chip.

RAM= All this bit does is set variable cardid equal to the first field of output from lspci matching "VGA" and feeds that as a request for -v verbose output from lspci for that specific -s device, further filtering the output by grep for the string " prefetchable" as this contains the memory on the card itself (note the preceding space as we don't want to match "non-prefetchable" in our output.

For clock rate on Intel integrated graphics (Tested on I3 and I5)

execute the command sudo find /sys -type f -name gt_cur* -print0 | xargs -0 cat This dives into the /sys tree to locate the gt_cur_freq_mhz file which on my I3 is /sys/devices/pci0000:00/0000:00:02.0/drm/card0/gt_cur_freq_mhz and prints the content. which in my case under extremely light load is 350 as in 350 MHz which corresponds to the minimum frequency found in /sys/devices/pci0000:00/0000:00:02.0/drm/card0/gt_min_freq_mhz and when running glxgears and glmark2 results in 1050 as in 1050 MHz which corresponds to the maximum frequency found in /sys/devices/pci0000:00/0000:00:02.0/drm/card0/gt_max_freq_mhz

For clock rates on nvidia cards:

nvidia-smi -stats -d procClk corresponds to the GPU clock nvidia-smi -stats -d memClk corresponds to the memory clock.

Note: I am unable to test the above as my trusty GeForce 210 isn't supported and this works only on Kepler or newer GPUs as indicated by `nvidia-smi -stats --help'

I do not currently have any solutions for clock rate on AMD cards and do not have the hardware available for testing. I will however say that to the best of my knowledge the aticonfig mentioned in the accepted answer no longer exists and it appears that nvclock isn't available for anything since trusty.

Answer 10

If you're looking for only the names of the video cards on the machine, then simply use:

$ nvidia-smi --list-gpus

For some newer GPUs, this also lists the memory of each device.

Answer 11

Conky or Terminal Splash Screen

I use two methods to automatically display nVidia GPU and Intel iGPU information:

• Conky dynamically displays GPU information in real time
• ~/.bashrc displays GPU information each time the terminal is opened

---

Conky real time display

This example uses Conky to display current GPU (nVidia or Intel) stats in real time. Conky is a light weight system monitor popular among many Linux enthusiasts.

The display changes depending on if you booted after prime-select intel or prime-select nvidia.

Intel iGPU

• The Intel iGPU shows as Skylake GT2 HD 530 iGPU with current frequency
• The Minimum frequency is 350 MHz and the Maximum is 1050 MHz

nVidia GPU

• The nVidia GPU shows as GeForce GTX970M with current GPU frequency and temperature
• The Driver version, P-State and BIOS version are displayed
• The GPU load, RAM use, Power Consumption and RAM frequency is displayed

Conky Code

Here is the relevant Conky script for Intel iGPU and nVidia GPU:

#------------+
# Intel iGPU |
#------------+
${color orange}${hr 1}${if_match "intel" == "${execpi 99999 prime-select query}"}
${color2}${voffset 5}Intel® Skylake GT2 HD 530 iGPU @${alignr}${color green}${execpi .001 (cat /sys/class/drm/card1/gt_cur_freq_mhz)} MHz
${color}${goto 13}Min. Freq:${goto 120}${color green}${execpi .001 (cat /sys/class/drm/card1/gt_min_freq_mhz)} MHz${color}${goto 210}Max. Freq:${alignr}${color green}${execpi .001 (cat /sys/class/drm/card1/gt_max_freq_mhz)} MHz
${color orange}${hr 1}${else}
#------------+
# Nvidia GPU |
#------------+
${color2}${voffset 5}${execpi .001 (nvidia-smi --query-gpu=gpu_name --format=csv,noheader)} ${color1}@ ${color green}${execpi .001 (nvidia-smi --query-gpu=clocks.sm --format=csv,noheader)} ${alignr}${color1}Temp: ${color green}${execpi .001 (nvidia-smi --query-gpu=temperature.gpu --format=csv,noheader)}°C
${color1}${voffset 5}Ver: ${color green}${execpi .001 (nvidia-smi --query-gpu=driver_version --format=csv,noheader)} ${color1} P-State: ${color green}${execpi .001 (nvidia-smi --query-gpu=pstate --format=csv,noheader)} ${alignr}${color1}BIOS: ${color green}${execpi .001 (nvidia-smi --query-gpu=vbios_version --format=csv,noheader)}
${color1}${voffset 5}GPU:${color green}${execpi .001 (nvidia-smi --query-gpu=utilization.gpu --format=csv,noheader)} ${color1}Ram:${color green}${execpi .001 (nvidia-smi --query-gpu=utilization.memory --format=csv,noheader)} ${color1}Pwr:${color green}${execpi .001 (nvidia-smi --query-gpu=power.draw --format=csv,noheader)} ${alignr}${color1}Freq: ${color green}${execpi .001 (nvidia-smi --query-gpu=clocks.mem --format=csv,noheader)}
${color orange}${hr 1}${endif}

---

~/.bashrc Terminal splash screen

This example modifies ~/.bashrc to display information on a splash screen each time the terminal is opened or whenever you type . .bashrc at the shell prompt.

In addition to neofetch answered previously, there is screenfetch which looks a lot nicer (IMO). Plus another answer mentions he doesn't know how to get iGPU listed and this does it:

For details on setup see: Terminal splash screen with Weather, Calendar, Time & Sysinfo?

In summary just for the bottom section with Ubuntu display containing GPU information (second last line) use:

sudo apt install screenfetch
screenfetch

You'll want to put the screenfetch command an the bottom of your ~/.bashrc file to have it appear every time you open the terminal.

Answer 12

Just to find the basics, according to https://wiki.debian.org/NvidiaGraphicsDrivers#NVIDIA_Proprietary_Driver,

lspci | grep VGA

If you need more detail than that, see @knb's answer to this same question.

Answer 13

For nvidia GPUs, nvidia-smi command is your friend. See man nvidia-smi if you like to.

For listing GPUs use nvidia-smi -L (nvidia-smi --list-gpus), nvidia-smi -q give information about the gpu and the running processes.

Answer 14

If you would like to have simple information, you could try gpustat. It is very good and simple.

The author gives the following installation instructions:

Install from PyPI:

pip install gpustat 

To install the latest version (master branch) via pip:

pip install git+https://github.com/wookayin/gpustat.git@master 

If you don't have root privilege, please try to install on user namespace: pip install --user. Note that from v0.4, gpustat.py is no more a zero-dependency executable. However, in rare cases you'll need a single executable script (legacy), you can also try:

wget https://raw.githubusercontent.com/wookayin/gpustat/v0.3.2/gpustat.py -O ~/.local/bin/gpustat chmod +x ~/.local/bin/gpustat    # Assuming ~/.local/bin is in your $PATH

Answer 15

If you have a AMD Radeon Card, you may want to run the following commands

sudo update-pciids #optional command, requires internet
lspci -nn | grep -E 'VGA|Display'

It should report something like this

00:01.0 VGA compatible controller [0300]: Advanced Micro Devices, Inc. [AMD/ATI] Wani [Radeon R5/R6/R7 Graphics] [1002:9874] (rev c5)
03:00.0 Display controller [0380]: Advanced Micro Devices, Inc. [AMD/ATI] Sun XT [Radeon HD 8670A/8670M/8690M / R5 M330 / M430 / R7 M520] [1002:6660] (rev ff)

Answer 16

Well, this answer assumes you have a server with NVIDIA-GPUs. You have three ways:

1. To get just a short gist: nvidia-smi

2. To get a detailed one : nvidia-smi -q. You'll get multiple screens of detailed info if you more than 1 gpu.

3. Do a ls /proc/driver/nvidia/gpus/. It'll display the GPU-bus location as folders. Now, run the following command for each of the gpu bus locations. Fill <gpu-id> with bus-location: cat /proc/driver/nvidia/gpus/<gpu_id>/information

Answer 17

If you're running Ubuntu on a Chromebook with crouton, the only one of the answers that will work is going to chrome://gpu in the Chrome browser.

Answer 18

For AMD based graphics card(GPU), you can use radeon-profile application to get detailed information about the cards. It provides temperature, clock, Vram usage etc. (Github repository link)

Step1: sudo add-apt-repository ppa:radeon-profile/stable

Step 2:

sudo apt update
sudo apt install radeon-profile

Step 3: run radeon-profile

Output screenshots (I have two GPU cards, card0(integrated) and card1(discrete)):

System specification:

• Ubuntu 20.04 LTS
• CPU: AMD® Ryzen 5 4600h
• GPU: AMD® Radeon rx 5600m

Source

Answer 19

For the Intel GMA950 (comes with EeePC in particular) you can run:

setpci -s 00:02.0 f0.b

which will return '00' for 200MHz, '01' for 250MHz or '03' for 400MHz. You may be able to apply the same principle to other Intel cards.

Answer 20

Use lspci , lspci -v to get basic info see here.

In my case for ex once I run lspci and I have got :

dina@dina-X450LA:~$ lspci
00:02.0 VGA compatible controller: Intel Corporation Haswell-ULT Integrated Graphics Controller (rev 0b)
00:03.0 Audio device: Intel Corporation Haswell-ULT HD Audio Controller (rev 0b)
00:14.0 USB controller: Intel Corporation 8 Series USB xHCI HC (rev 04)
00:16.0 Communication controller: Intel Corporation 8 Series HECI #0 (rev 04)
00:1b.0 Audio device: Intel Corporation 8 Series HD Audio Controller (rev 04)
00:1c.0 PCI bridge: Intel Corporation 8 Series PCI Express Root Port 1 (rev e4)
00:1c.2 PCI bridge: Intel Corporation 8 Series PCI Express Root Port 3 (rev e4)
00:1c.3 PCI bridge: Intel Corporation 8 Series PCI Express Root Port 4 (rev e4)
00:1d.0 USB controller: Intel Corporation 8 Series USB EHCI #1 (rev 04)
00:1f.0 ISA bridge: Intel Corporation 8 Series LPC Controller (rev 04)
00:1f.2 SATA controller: Intel Corporation 8 Series SATA Controller 1 [AHCI mode] (rev 04)
00:1f.3 SMBus: Intel Corporation 8 Series SMBus Controller (rev 04)
02:00.0 Ethernet controller: Qualcomm Atheros QCA8171 Gigabit Ethernet (rev 10)
03:00.0 Network controller: Ralink corp. RT3290 Wireless 802.11n 1T/1R PCIe
03:00.1 Bluetooth: Ralink corp. RT3290 Bluetooth

Answer 21

In order to get all the information about the graphics processor, you can use the following command as specified by @greyfade.

> glxinfo

However, if the program glxinfo is currently not installed, you can install it by typing:

> sudo apt install mesa-utils

You will also have to enable the component called universe. Once this is done, glxinfo will list all the specifications related to the graphics processor in that environment.

Answer 22

Tested for GTX 1080Ti - For clock rates on nvidia card -

nvidia-smi stats -d procClk corresponds to the Core clock 
nvidia-smi stats -d memClk corresponds to the Memory clock

---

For monitoring every second -

watch -n 1 nvidia-smi stats -d procClk -c 1

---

For monitoring a subset of the devices every second -

watch -n 1 nvidia-smi stats -d procClk -c 1 -i 0,1

Based off on Elder Geek's answer with modifications to print every second to check for thermal throttling. If your GPU is being throttled, the procClk will drop significantly.

Answer 23

For checking the utilization of Intel GPUs there is intel_gpu_top available since xenial (https://packages.ubuntu.com/bionic/intel-gpu-tools).

apt-get install intel-gpu-tools

There are just a few options available - see man intel_gpu_top.

Answer 24

Like in Chromium, if you have Firefox: about:support

Answer 25

For my setup this is the cleanest:

python -c "import torch; print(torch.cuda.get_device_name(0));"

or

python -c "import uutils; gpu_name_otherwise_cpu(print_to_stdout=True);"

code:

def gpu_name_otherwise_cpu(print_to_stdout: bool = False):
    gpu_name_or_cpu = None
    try:
        gpu_name_or_cpu = torch.cuda.get_device_name(0)
    except:
        device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
        gpu_name_or_cpu = device
    print(f'{gpu_name_or_cpu=}') if print_to_stdout else None
    return gpu_name_or_cpu